Team · Research Staff
Emily Vosper
Senior Research Associate
My interest lies in how we can apply AI in a meaningful way to help navigate the climate crisis. My work involves applying interpretable machine learning techniques to develop models that aid in climate risk estimation.
My PhD focused on enhancing the resolution of tropical cyclone rainfall using generative machine learning techniques. By working with generative models, I was able to produce high-resolution rainfall estimates for 28,000 synthetic tropical cyclone events in the order of hours. I have found that machine learning can complement climate science by delivering tangible efficiency savings without sacrificing performance.
Projects
- BREATHE Funded project
Bridging Research on Environmental Attribution and Health Equity - CHAI PI Funded project
Using diffusion models to enhance coarse, health-relevant climate model data to 2.2–5 km, 3-hourly resolution over the UK climate, so that we can better understand how extreme weather affects health, particularly maternal health and hospitalisation. - DELTA Funded project
Downscaled Ensemble for Local-scale Trend Attribution. An open data platform that provides bias-corrected, downscaled temperature and precipitation timeseries for every country, under both observed and counterfactual (no human influence) climates, so that health researchers can carry out climate change attribution studies without having to process climate model data themselves.